AUSTIN, Texas — Osteoarthritis of the knee is one of the most common forms of arthritis, affecting more than 30 million Americans. Treatments range from physical therapy to joint injections to total knee replacement surgery. In a new study published in JAMA Network Open, a team from UT Health Austin’s Musculoskeletal Institute found that a decision aid powered by artificial intelligence (AI) can help patients and their doctors determine which course of treatment is most appropriate, and improve health outcomes.
The team at UT Health Austin, the clinical practice of Dell Medical School at The University of Texas at Austin, developed the decision aid in collaboration with a digital health company. The aid uses AI to enhance shared decision making around treatment options. It works by combining a patient’s clinical data with patient-reported outcome measurements — surveys completed by patients that include detailed information about how knee arthritis affects their everyday lives.
“The AI software processes an array of data and calculates a personalized score for an individual patient that predicts their outcomes if they chose to undergo knee surgery,” said lead study author Prakash Jayakumar, M.D., assistant professor of Surgery and Perioperative Care at Dell Med. “And it’s all done before the patient and doctor even meet for their initial consultation. It’s a powerful tool providing insights that we’ve never had before—a true game-changer.”
In the study, Jayakumar and his colleagues used a randomized controlled trial to compare outcomes between two patient groups: One used the AI-enabled decision aid, combined with education materials and preference-setting tasks. Patients in the other group made their treatment decision after receiving only the education materials.
The group using the AI technology, education and preference-setting tasks showed:
- Higher levels of decision quality and shared decision-making;
- Increased patient satisfaction;
- And better functional outcomes, compared to patients who only received educational materials.
“We also found that the decision aid produces positive outcomes from patients of all backgrounds, regardless of employment status or type of insurance—including those who traditionally feel less empowered to make informed decisions,” said Jayakumar. “Patients who used the aid fared better physically, as well. We think that’s because it promotes patient engagement, making them equal partners in their health care team and the decision-making process.”
For clinicians, the high-tech tool can clarify a patient’s fears and preferences around surgery, and help them better-manage patient expectations.
“This demonstrates the benefits of a personalized, data-driven approach to shared-decision making for patients considering total knee replacement—a benefit which could have far-reaching consequences for populations suffering from knee osteoarthritis,” said Jayakumar.